MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model
This work addresses a frontier in expressive digital human creation for applications like animation and virtual reality, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackles the problem of generating realistic Human-Object Interaction (HOI) videos with complex non-planar motions, such as out-of-plane reorientation, by proposing MVHOI, a two-stage framework that uses a 3D Foundation Model and a controllable video generation model to achieve superior performance in long-duration HOI video synthesis.
Human-Object Interaction (HOI) video reenactment with realistic motion remains a frontier in expressive digital human creation. Existing approaches primarily handle simple image-plane motion (e.g., in-plane translations), struggling with complex non-planar manipulations like out-of-plane reorientation. In this paper, we propose MVHOI, a two-stage HOI video reenactment framework that bridges multi-view reference conditions and video foundation models via a 3D Foundation Model (3DFM). The 3DFM first produces view-consistent object priors conditioned on implicit motion dynamics across novel viewpoints. A controllable video generation model then synthesizes high-fidelity object texture by incorporating multi-view reference images, ensuring appearance consistency via a reasonable retrieval mechanism. By enabling these two stages to mutually reinforce one another during the inference phase, our framework shows superior performance in generating long-duration HOI videos with intricate object manipulations. Extensive experiments show substantial improvements over prior approaches, especially for HOI with complex 3D object manipulations.